{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/refining-activation-downsampling-with","title":"Refining activation downsampling with SoftPool","arxiv_id":"2101.00440","date":"2021-01-02","proceeding":"ICCV 2021 10","authors":["Alexandros Stergiou","Ronald Poppe","Grigorios Kalliatakis"],"abstract":"Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to reduce computational requirements of subsequent convolutions. An important feature of the pooling operation is the minimization of information loss, with respect to the initial activation maps, without a significant impact on the computation and memory overhead. To meet these requirements, we propose SoftPool: a fast and efficient method for exponentially weighted activation downsampling. Through experiments across a range of architectures and pooling methods, we demonstrate that SoftPool can retain more information in the reduced activation maps. This refined downsampling leads to improvements in a CNN's classification accuracy. Experiments with pooling layer substitutions on ImageNet1K show an increase in accuracy over both original architectures and other pooling methods. We also test SoftPool on video datasets for action recognition. Again, through the direct replacement of pooling layers, we observe consistent performance improvements while computational loads and memory requirements remain limited.","url_abs":"https://arxiv.org/abs/2101.00440v3","url_pdf":"https://arxiv.org/pdf/2101.00440v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"refining-activation-downsampling-with","repo_url":"https://github.com/alexandrosstergiou/SoftPool","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"refining-activation-downsampling-with","repo_url":"https://github.com/sayakpaul/Revisiting-Pooling-in-CNNs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"refining-activation-downsampling-with","repo_url":"https://github.com/HelloDuoLA/refining-activation-downsampling-with-SoftPool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"refining-activation-downsampling-with","repo_url":"https://github.com/MindCode-4/code-13/tree/main/refining-activation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"refining-activation-downsampling-with","repo_url":"https://github.com/MindCode-4/code-8/tree/main/refining-activation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"refining-activation-downsampling-with","repo_url":"https://github.com/MindSpore-scientific/code-14/tree/main/refining-activation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"refining-activation-downsampling-with","repo_url":"https://github.com/MindSpore-scientific/code-5/tree/main/refining-activation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"refining-activation-downsampling-with","repo_url":"https://github.com/qwopqwop200/SoftPool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"}],"methods":[{"method_slug":"softpool","method_name":"SoftPool"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.00440","atlas_url":"https://app.syntology.ai/?focus=2101.00440","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2101.00440"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2101.00440\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2101.00440"},"call":"get_concepts_for_paper(arxiv_id=\"2101.00440\")"}],"by_repo":[{"repo":"alexandrosstergiou/SoftPool","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sayakpaul/Revisiting-Pooling-in-CNNs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"HelloDuoLA/refining-activation-downsampling-with-SoftPool","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindCode-4/code-13","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2212.08663"],"harvested_for_calls":[{"arxiv_id":"2212.08663","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2212.08663"},"call":"get_harvested_code_for_paper(arxiv_id=\"2212.08663\")"}]},{"repo":"MindCode-4/code-8","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2103.13843"],"harvested_for_calls":[{"arxiv_id":"2103.13843","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.13843"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.13843\")"}]},{"repo":"MindSpore-scientific/code-14","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2306.01116"],"harvested_for_calls":[{"arxiv_id":"2306.01116","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.01116"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.01116\")"}]},{"repo":"MindSpore-scientific/code-5","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.06329"],"harvested_for_calls":[{"arxiv_id":"2305.06329","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.06329"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.06329\")"}]},{"repo":"qwopqwop200/SoftPool","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"75566c06b9e11afede77643ec50b0aac1a0377f9ad29e2688729096e2cdd46c3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}